RobustRDP

Fine-tuned model for the paper: RobustRDP: Advancing Reaction Diagram Parsing via Synthetic-to-Real Data Scaling and Robustness-Oriented Training.

Description

This model is a fine-tuned checkpoint based on Qwen2.5-VL-3B-Instruct, trained with a three-stage pipeline:

1. Pretrain stage: Synthetic data pretraining on large-scale synthetic reaction diagrams.
2. SFT stage: Supervised fine-tuning with three specialized tasks:
   • Vanilla Reaction Parsing (VRP): Standard reaction diagram parsing
   • Region-Guided Reaction Parsing (RGRP): Region-aware parsing with spatial guidance
   • Prefix-Perturbed Reaction Parsing (PPRP): Robustness-oriented parsing with prefix perturbations
3. DPO stage: Direct Preference Optimization to further align model outputs with ground-truth annotations.

Training Details

Config	Pretrain	SFT	DPO
Base Model	Qwen2.5-VL-3B-Instruct	Qwen2.5-VL-3B-Instruct	Qwen2.5-VL-3B-Instruct
Learning Rate	1.0×10⁻⁶	1.0×10⁻⁵	3.0×10⁻⁷
Batch Size	16	4	64
Epochs	1	1	1
Scheduler	Cosine (warmup 0.03)	Cosine (warmup 0.03)	Cosine (warmup 0.03)
Optimizer	AdamW	AdamW	AdamW
Trainable Params	LLM only	Full (vision + LLM)	LLM only

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Jingcz/RobustRDP"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

Related Resources

• Dataset: RxnLabelData
• Annotation Platform: RxnLabel